LeashIndex Get the report

Index / devtools

com.mcparmory/gitlab

com-mcparmory-gitlab declares 53 capabilities across 53 tools, with 2 critical issues.

98/100 exposureHigh exposure

Manifest recorded 2026-10-11 from tools/list answered by the PyPI package mcparmory-gitlab==1.0.3 (published to PyPI as mcparmory-gitlab, listed in the official MCP registry as com.mcparmory/gitlab 1.0.3), run in an isolated container with no network access and no credentials. The date changes only when the manifest does. Not verified by a maintainer.

Issues

These describe what this server's manifest declares. A product can provide controls that MCP has no way to express — token revocation, an admin console, audit logs — and this page cannot see them. The absence of a declaration is not evidence that a control is absent.

critical · no-revocation · All 53 tools

53 of 53 tools declare no way for the customer to switch them off once granted. This applies to every tool because MCP has no field in which to declare a revocation mechanism; the product may provide one outside MCP that a manifest cannot show.

critical · irreversible-uncapped · 12 of 53 tools

12 tools are classified as irreversible and declare no limit.

high · no-expiry · All 53 tools

53 of 53 tools declare no expiry. This applies to every tool because MCP has no field in which to declare an expiry; the product may provide one outside MCP that a manifest cannot show.

high · no-audit-trail · All 53 tools

53 of 53 tools declare no record of their actions that the customer can read. This applies to every tool because MCP has no field in which to declare an audit requirement; the product may provide one outside MCP that a manifest cannot show.

high · uncapped-write · 18 of 53 tools

18 tools can modify data and declare no limit.

low · uncapped-read · 23 of 53 tools

23 tools can read data and declare no limit.

Declared capabilities

How each tool was read. declared means the server's own annotation said so — self-reported and unverified. inferred is from the tool's name. assumed means nothing indicated either way.

ToolRead asBasis
get_group_badgeread declared
update_group_badgewrite inferred
remove_group_badgedestructive declared
list_group_badgesread declared
add_group_badgewrite inferred
deny_group_access_requestdestructive declared
approve_group_access_requestwrite inferred
list_group_access_requestsread declared
request_group_accesswrite inferred
delete_merged_branchesdestructive declared
get_branchread declared
delete_branchdestructive declared
check_branch_existsread declared
list_repository_branchesread declared
create_branchwrite inferred
unprotect_branchdestructive declared
protect_branchwrite inferred
get_project_badgeread declared
update_project_badgewrite inferred
delete_badgedestructive declared
list_project_badgesread declared
create_project_badgewrite inferred
deny_access_requestdestructive declared
approve_access_requestwrite inferred
list_access_requestsread declared
request_project_accesswrite inferred
update_alert_metric_imagewrite inferred
delete_alert_metric_imagedestructive declared
list_alert_metric_imagesread declared
upload_alert_metric_imagewrite inferred
pause_batched_background_migrationwrite assumed
get_admin_ci_variableread declared
delete_instance_variabledestructive declared
list_instance_variablesread declared
create_instance_variablewrite inferred
get_clusterread declared
update_clusterwrite inferred
delete_clusterdestructive declared
add_kubernetes_clusterwrite inferred
list_clustersread declared
delete_applicationdestructive declared
get_user_avatarread declared
get_broadcast_messageread declared
delete_broadcast_messagedestructive declared
get_migration_entityread declared
list_migration_entitiesread declared
get_bulk_importread declared
list_migration_entities_allread declared
list_migrationsread declared
start_bulk_migrationwrite assumed
list_jobsread declared
get_jobread declared
execute_manual_jobwrite assumed
Answering this question about your own agent? The self-serve stack report applies the same reading to your own stack or server and gives you a dated document you can hand to a customer's security review. It is generated in your browser, with nobody to wait for. Buying one does not change this page, its score or its place in the index — see Independence.
Maintain this server? If this page misreads your manifest, or your server has changed, submit its current tools/list response and it will be re-scored and dated. Corrections are published alongside the original, not in place of it.